Privacy-preserving data generation and sharing using identification sanitizer

Shuo Wang, Lingjuan Lyu, Tianle Chen, Shangyu Chen, Surya Nepal, Carsten Rudolph, Marthie Grobler

Research output: Chapter in Book/Report/Conference proceedingConference PaperResearchpeer-review


In this paper, we propose a practical privacy-preserving generative model for data sanitization and sharing, called Sanitizer-Variational Autoencoder (SVAE). We assume that the data consists of identification-relevant and irrelevant components. A variational autoencoder (VAE) based sanitization model is proposed to strip the identification-relevant features and only retain identification-irrelevant components in a privacy-preserving manner. The sanitization allows for task-relevant discrimination (utility) but minimizes the personal identification information leakage (privacy). We conduct extensive empirical evaluations on the real-world face, biometric signal and speech datasets, and validate the effectiveness of our proposed SVAE, as well as the robustness against the membership inference attack.

Original languageEnglish
Title of host publicationWeb Information Systems Engineering – WISE 2020
Subtitle of host publication21st International Conference Amsterdam, The Netherlands, October 20–24, 2020 Proceedings, Part II
EditorsZhisheng Huang, Wouter Beek, Hua Wang, Rui Zhou, Yanchun Zhang
Place of PublicationCham Switzerland
Number of pages16
ISBN (Electronic)9783030620080
ISBN (Print)9783030620073
Publication statusPublished - 2020
EventInternational Conference on Web Information Systems Engineering 2020 - Amsterdam, Netherlands
Duration: 20 Oct 202024 Oct 2020
Conference number: 21st (Proceedings) (Website)

Publication series

NameLecture Notes in Computer Science
NumberPart II
ISSN (Print)0302-9743
ISSN (Electronic)1611-3349


ConferenceInternational Conference on Web Information Systems Engineering 2020
Abbreviated titleWISE 2020
Internet address


  • Data sharing
  • Deep learning
  • Generative model
  • Privacy-preserving
  • Variational autoencoder

Cite this